FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3016366012> ?p ?o ?g. }

• W3016366012 abstract "Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown. Existing methods attempt to address this challenge by transferring image styles or aligning feature distributions across domains, whereas the rich unlabeled samples in target domains are not sufficiently exploited. This paper presents a novel augmented discriminative clustering (AD-Cluster) technique that estimates and augments person clusters in target domains and enforces the discrimination ability of re-ID models with the augmented clusters. AD-Cluster is trained by iterative density-based clustering, adaptive sample augmentation, and discriminative feature learning. It learns an image generator and a feature encoder which aim to maximize the intra-cluster diversity in the sample space and minimize the intra-cluster distance in the feature space in an adversarial min-max manner. Finally, AD-Cluster increases the diversity of sample clusters and improves the discrimination capability of re-ID models greatly. Extensive experiments over Market-1501 and DukeMTMC-reID show that AD-Cluster outperforms the state-of-the-art with large margins." @default.
• W3016366012 created "2020-04-24" @default.
• W3016366012 creator A5010479652 @default.
• W3016366012 creator A5015317495 @default.
• W3016366012 creator A5016080094 @default.
• W3016366012 creator A5023507910 @default.
• W3016366012 creator A5023918894 @default.
• W3016366012 creator A5032932242 @default.
• W3016366012 creator A5045281526 @default.
• W3016366012 date "2020-04-19" @default.
• W3016366012 modified "2023-09-25" @default.
• W3016366012 title "AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification" @default.
• W3016366012 cites W1565327149 @default.
• W3016366012 cites W1577269164 @default.
• W3016366012 cites W1673310716 @default.
• W3016366012 cites W1722318740 @default.
• W3016366012 cites W1731081199 @default.
• W3016366012 cites W180242331 @default.
• W3016366012 cites W1949591461 @default.
• W3016366012 cites W2108598243 @default.
• W3016366012 cites W2148349024 @default.
• W3016366012 cites W2150846797 @default.
• W3016366012 cites W2151575489 @default.
• W3016366012 cites W2159291411 @default.
• W3016366012 cites W2194775991 @default.
• W3016366012 cites W2204750386 @default.
• W3016366012 cites W2212660284 @default.
• W3016366012 cites W2511791013 @default.
• W3016366012 cites W2520433280 @default.
• W3016366012 cites W2551835155 @default.
• W3016366012 cites W2560977758 @default.
• W3016366012 cites W2585635281 @default.
• W3016366012 cites W2598634450 @default.
• W3016366012 cites W2778652957 @default.
• W3016366012 cites W2798681837 @default.
• W3016366012 cites W2799185441 @default.
• W3016366012 cites W2883725317 @default.
• W3016366012 cites W2896016251 @default.
• W3016366012 cites W2898047322 @default.
• W3016366012 cites W2948398419 @default.
• W3016366012 cites W2957037461 @default.
• W3016366012 cites W2962687275 @default.
• W3016366012 cites W2962808524 @default.
• W3016366012 cites W2962852342 @default.
• W3016366012 cites W2962859295 @default.
• W3016366012 cites W2963000559 @default.
• W3016366012 cites W2963118547 @default.
• W3016366012 cites W2963275094 @default.
• W3016366012 cites W2963557071 @default.
• W3016366012 cites W2963767194 @default.
• W3016366012 cites W2963784072 @default.
• W3016366012 cites W2963826681 @default.
• W3016366012 cites W2963975998 @default.
• W3016366012 cites W2963983343 @default.
• W3016366012 cites W2963989829 @default.
• W3016366012 cites W2964074409 @default.
• W3016366012 cites W2964260687 @default.
• W3016366012 cites W2970575838 @default.
• W3016366012 cites W2988852559 @default.
• W3016366012 cites W2997114618 @default.
• W3016366012 cites W2999929549 @default.
• W3016366012 cites W3007744269 @default.
• W3016366012 cites W3009238880 @default.
• W3016366012 cites W3009761962 @default.
• W3016366012 doi "https://doi.org/10.48550/arxiv.2004.08787" @default.
• W3016366012 hasPublicationYear "2020" @default.
• W3016366012 type Work @default.
• W3016366012 sameAs 3016366012 @default.
• W3016366012 citedByCount "3" @default.
• W3016366012 countsByYear W30163660122021 @default.
• W3016366012 crossrefType "posted-content" @default.
• W3016366012 hasAuthorship W3016366012A5010479652 @default.
• W3016366012 hasAuthorship W3016366012A5015317495 @default.
• W3016366012 hasAuthorship W3016366012A5016080094 @default.
• W3016366012 hasAuthorship W3016366012A5023507910 @default.
• W3016366012 hasAuthorship W3016366012A5023918894 @default.
• W3016366012 hasAuthorship W3016366012A5032932242 @default.
• W3016366012 hasAuthorship W3016366012A5045281526 @default.
• W3016366012 hasBestOaLocation W30163660121 @default.
• W3016366012 hasConcept C116834253 @default.
• W3016366012 hasConcept C121332964 @default.
• W3016366012 hasConcept C134306372 @default.
• W3016366012 hasConcept C138885662 @default.
• W3016366012 hasConcept C153180895 @default.
• W3016366012 hasConcept C154945302 @default.
• W3016366012 hasConcept C163258240 @default.
• W3016366012 hasConcept C164866538 @default.
• W3016366012 hasConcept C185592680 @default.
• W3016366012 hasConcept C198531522 @default.
• W3016366012 hasConcept C199360897 @default.
• W3016366012 hasConcept C2776401178 @default.
• W3016366012 hasConcept C2780992000 @default.
• W3016366012 hasConcept C33923547 @default.
• W3016366012 hasConcept C36503486 @default.
• W3016366012 hasConcept C41008148 @default.
• W3016366012 hasConcept C41895202 @default.
• W3016366012 hasConcept C43617362 @default.
• W3016366012 hasConcept C59404180 @default.
• W3016366012 hasConcept C59822182 @default.
• W3016366012 hasConcept C62520636 @default.

• next